{"id":"https://openalex.org/W7225754995","doi":"https://doi.org/10.66977/xsci.2611.001v","title":"Can the Confidence and Decisions of System 1 Models Be Trusted? An Explainability and Perturbation Audit of JevStyle Decision Models","display_name":"Can the Confidence and Decisions of System 1 Models Be Trusted? An Explainability and Perturbation Audit of JevStyle Decision Models","publication_year":2026,"publication_date":"2026-11-12","ids":{"openalex":"https://openalex.org/W7225754995","doi":"https://doi.org/10.66977/xsci.2611.001v"},"language":"en","primary_location":{"id":"doi:10.66977/xsci.2611.001v","doi":"https://doi.org/10.66977/xsci.2611.001v","is_oa":false,"landing_page_url":"https://doi.org/10.66977/xsci.2611.001v","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"posted-content"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2611.12521","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5017309914","display_name":"Julien Delaunay","orcid":"https://orcid.org/0009-0001-9247-5745","observed_orcids":["https://orcid.org/0009-0001-9247-5745","https://orcid.org/0000-0001-6824-5010"]},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Julien Delaunay","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":["https://openalex.org/A5017309914"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.9721999764442444,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.9721999764442444,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.025299999862909317,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10883","display_name":"Ethics and Social Impacts of AI","score":0.00039999998989515007,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/jev","display_name":"Jev","score":0.7609999775886536},{"id":"https://openalex.org/keywords/deterministic-inference","display_name":"deterministic inference","score":0.3269999921321869},{"id":"https://openalex.org/keywords/statistical-calibration","display_name":"statistical calibration","score":0.6230000257492065},{"id":"https://openalex.org/keywords/explainability","display_name":"explainability","score":0.5590000152587891},{"id":"https://openalex.org/keywords/prompt-injection-defense","display_name":"prompt injection defense","score":0.8029999732971191},{"id":"https://openalex.org/keywords/clinical-triage","display_name":"clinical triage","score":0.9190000295639038},{"id":"https://openalex.org/keywords/kernelshap","display_name":"KernelSHAP","score":0.6389999985694885},{"id":"https://openalex.org/keywords/low-latency-routing","display_name":"low-latency routing","score":0.5649999976158142},{"id":"https://openalex.org/keywords/han","display_name":"Han","score":0.46700000762939453}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7455000281333923},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.46399998664855957},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.45840001106262207},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4487999975681305},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.3926999866962433},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3797000050544739},{"id":"https://openalex.org/C3309909","wikidata":"https://www.wikidata.org/wiki/Q864155","display_name":"Binary decision diagram","level":2,"score":0.3621000051498413},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.3571000099182129},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.3547999858856201},{"id":"https://openalex.org/C59594135","wikidata":"https://www.wikidata.org/wiki/Q5249242","display_name":"Decision model","level":2,"score":0.3476000130176544},{"id":"https://openalex.org/C125112378","wikidata":"https://www.wikidata.org/wiki/Q176640","display_name":"Randomness","level":2,"score":0.34459999203681946},{"id":"https://openalex.org/C70437156","wikidata":"https://www.wikidata.org/wiki/Q7228652","display_name":"Pooling","level":2,"score":0.33500000834465027},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.3334999978542328},{"id":"https://openalex.org/C2780033181","wikidata":"https://www.wikidata.org/wiki/Q24962805","display_name":"Decision aids","level":3,"score":0.31859999895095825},{"id":"https://openalex.org/C165838908","wikidata":"https://www.wikidata.org/wiki/Q736777","display_name":"Calibration","level":2,"score":0.31610000133514404},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.30809998512268066},{"id":"https://openalex.org/C2780695315","wikidata":"https://www.wikidata.org/wiki/Q3799040","display_name":"Unobservable","level":2,"score":0.30799999833106995},{"id":"https://openalex.org/C48372109","wikidata":"https://www.wikidata.org/wiki/Q3913","display_name":"Binary number","level":2,"score":0.3057999908924103},{"id":"https://openalex.org/C151319957","wikidata":"https://www.wikidata.org/wiki/Q752739","display_name":"Asynchronous communication","level":2,"score":0.305400013923645},{"id":"https://openalex.org/C160234255","wikidata":"https://www.wikidata.org/wiki/Q812535","display_name":"Bayesian inference","level":3,"score":0.3043999969959259},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.296099990606308},{"id":"https://openalex.org/C160403385","wikidata":"https://www.wikidata.org/wiki/Q220543","display_name":"Queue","level":2,"score":0.2957000136375427},{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.29350000619888306},{"id":"https://openalex.org/C188441871","wikidata":"https://www.wikidata.org/wiki/Q7554146","display_name":"Softmax function","level":3,"score":0.29330000281333923},{"id":"https://openalex.org/C87007009","wikidata":"https://www.wikidata.org/wiki/Q210832","display_name":"Statistical hypothesis testing","level":2,"score":0.2924000024795532},{"id":"https://openalex.org/C84525736","wikidata":"https://www.wikidata.org/wiki/Q831366","display_name":"Decision tree","level":2,"score":0.28839999437332153},{"id":"https://openalex.org/C44492722","wikidata":"https://www.wikidata.org/wiki/Q327069","display_name":"Conditional probability","level":2,"score":0.28189998865127563},{"id":"https://openalex.org/C196083921","wikidata":"https://www.wikidata.org/wiki/Q7915758","display_name":"Variance (accounting)","level":2,"score":0.27970001101493835},{"id":"https://openalex.org/C107327155","wikidata":"https://www.wikidata.org/wiki/Q330268","display_name":"Decision support system","level":2,"score":0.2757999897003174},{"id":"https://openalex.org/C100660578","wikidata":"https://www.wikidata.org/wiki/Q18733","display_name":"Recall","level":2,"score":0.27390000224113464},{"id":"https://openalex.org/C187691185","wikidata":"https://www.wikidata.org/wiki/Q2020720","display_name":"Grid","level":2,"score":0.2736999988555908},{"id":"https://openalex.org/C33724603","wikidata":"https://www.wikidata.org/wiki/Q812540","display_name":"Bayesian network","level":2,"score":0.27320000529289246},{"id":"https://openalex.org/C2781003394","wikidata":"https://www.wikidata.org/wiki/Q737372","display_name":"Alphanumeric","level":2,"score":0.27320000529289246},{"id":"https://openalex.org/C140146324","wikidata":"https://www.wikidata.org/wiki/Q1144319","display_name":"Predicate (mathematical logic)","level":2,"score":0.2655999958515167},{"id":"https://openalex.org/C159877910","wikidata":"https://www.wikidata.org/wiki/Q2202883","display_name":"Autoregressive model","level":2,"score":0.26339998841285706},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.26330000162124634},{"id":"https://openalex.org/C28901747","wikidata":"https://www.wikidata.org/wiki/Q177571","display_name":"Decision theory","level":2,"score":0.2614000141620636},{"id":"https://openalex.org/C2779182362","wikidata":"https://www.wikidata.org/wiki/Q17126187","display_name":"Session (web analytics)","level":2,"score":0.2603999972343445},{"id":"https://openalex.org/C84839998","wikidata":"https://www.wikidata.org/wiki/Q5249245","display_name":"Decision rule","level":2,"score":0.2597000002861023},{"id":"https://openalex.org/C22684755","wikidata":"https://www.wikidata.org/wiki/Q847526","display_name":"Queueing theory","level":2,"score":0.2590000033378601}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.66977/xsci.2611.001v","doi":"https://doi.org/10.66977/xsci.2611.001v","is_oa":false,"landing_page_url":"https://doi.org/10.66977/xsci.2611.001v","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"posted-content"},{"id":"pmh:oai:arXiv.org:2611.12521","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2611.12521","pdf_url":"https://arxiv.org/pdf/2611.12521","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2611.12521","doi":"https://doi.org/10.48550/arxiv.2611.12521","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2611.12521","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2611.12521","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2611.12521","pdf_url":"https://arxiv.org/pdf/2611.12521","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7225754995.pdf","grobid_xml":"https://content.openalex.org/works/W7225754995.grobid-xml"},"referenced_works_count":7,"referenced_works":["https://openalex.org/W4285429195","https://openalex.org/W4327810158","https://openalex.org/W4385327568","https://openalex.org/W4387561528","https://openalex.org/W4401306886","https://openalex.org/W4401660192","https://openalex.org/W4404780965"],"related_works":["https://openalex.org/W7224091991","https://openalex.org/W7225156383","https://openalex.org/W7221563587","https://openalex.org/W7214038975","https://openalex.org/W7213432417","https://openalex.org/W7214915851","https://openalex.org/W7225198829","https://openalex.org/W7216480538","https://openalex.org/W7214588512","https://openalex.org/W7161102297"],"abstract_inverted_index":{"\"System":[0],"1\"":[1],"decision":[2,54],"models":[3,55,70,166,198],"(pioneered":[4],"by":[5],"TypeSafe":[6],"AI's":[7],"Jev)":[8],"replace":[9],"autoregressive":[10],"text":[11],"generation":[12],"with":[13,167,204,232],"a":[14,233],"single":[15],"forward":[16],"pass":[17],"returning":[18],"typed":[19],"probability":[20],"distributions":[21],"over":[22],"declared":[23],"schemas":[24],"(Choice,":[25],"Score,":[26],"Noul).":[27],"While":[28],"deployed":[29],"for":[30,192],"low-latency":[31],"routing":[32],"and":[33,39,63,84,106,173,187,209,218],"automated":[34],"triage,":[35],"their":[36],"statistical":[37],"calibration":[38,57],"post-hoc":[40,64],"explainability":[41],"remain":[42],"uncharacterized.":[43],"We":[44],"introduce":[45],"an":[46,107,119],"open,":[47],"deterministic":[48],"audit":[49],"benchmark":[50],"evaluating":[51],"System":[52,76,164],"1":[53,165],"across":[56,89],"under":[58,176],"label-preserving":[59],"perturbations,":[60],"cross-question":[61,148],"interference,":[62],"attribution":[65],"faithfulness.":[66],"Evaluating":[67],"five":[68,113],"open-weight":[69],"(0.8B":[71],"to":[72,151,159,182,201,206,215,227,245,251],"27B)":[73],"alongside":[74],"generative":[75],"2":[77],"baselines":[78],"--":[79,88],"both":[80],"single-token":[81],"logprob":[82,185],"scoring":[83],"structured":[85],"JSON/CoT":[86],"decoding":[87],"NLI":[90],"(e-SNLI),":[91],"adversarial":[92],"syntactic":[93,177],"shortcuts":[94],"(HANS),":[95],"synthetic":[96],"clinical":[97],"triage":[98],"(N=900),":[99],"prompt":[100],"injection":[101],"defense":[102,194],"(Tensor":[103],"Trust,":[104],"N=250),":[105],"86-case":[108],"logic-gate":[109],"trigger":[110],"suite":[111],"yields":[112],"findings:":[114],"(1)":[115],"provider":[116],"confidence":[117],"is":[118],"exact":[120],"closed-form":[121],"dispersion":[122],"transform":[123],"(1":[124],"-":[125],"H(p)/ln":[126],"K":[127],"on":[128,133,155,161,240],"sub-10B":[129],"models;":[130],"normalized":[131],"margin":[132],"Clef-27B)":[134],"rather":[135],"than":[136,184],"empirical":[137],"accuracy;":[138],"(2)":[139],"bundling":[140],"multiple":[141],"questions":[142],"in":[143,253],"one":[144],"request":[145],"induces":[146],"directional":[147],"interference":[149],"(11.7%":[150],"22.4%":[152],"binary":[153],"flips":[154],"Tev1-0.8B,":[156],"vs.":[157,249],"0.1%":[158],"0.2%":[160],"Tev1-4B);":[162],"(3)":[163],">=":[168,196],"4B":[169,197],"parameters":[170],"are":[171],"faster":[172],"better":[174],"calibrated":[175],"shifts":[178],"(ECE_w":[179],"=":[180,257],"0.030":[181],"0.087)":[183],"(0.144)":[186],"JSON":[188],"(0.378)":[189],"baselines;":[190],"(4)":[191],"prompt-injection":[193],"(N=250),":[195],"achieve":[199],"0.988":[200],"0.998":[202],"AUROC":[203],"up":[205],"95.2%":[207],"recall":[208],"0.0%":[210],"false":[211],"alarms":[212],"at":[213],"48":[214],"60":[216],"ms;":[217],"(5)":[219],"single-pass":[220],"inference":[221],"makes":[222],"512-coalition":[223],"XAI":[224],"interactive":[225],"(1.3":[226],"3.2":[228],"s/input),":[229],"while":[230],"KernelSHAP":[231],"logit":[234],"link":[235],"(S1-SHAP)":[236],"mitigates":[237],"softmax":[238],"saturation":[239],"disjunctive":[241],"OR":[242],"gates":[243],"(89.3%":[244],"100.0%":[246],"gate":[247],"recovery":[248],"57.1%":[250],"82.1%":[252],"prob":[254],"space;":[255],"p_adj":[256],"0.004).":[258]},"counts_by_year":[],"updated_date":"2026-11-13T13:42:25.865203","created_date":"2026-11-11T00:00:00"}